Figurative and Cultural Knowledge in LLMs: Investigating Cross-Domain Transfer through Fine-Tuning

2026-08-18

AI Summary

研究通过在文化数据上微调大型语言模型，探讨其对隐喻语言理解的影响。结果表明，诗歌微调可提升成语理解，但文化微调降低谚语解释准确性。

Abstract

Figurative language is deeply culturally embedded; fluent use requires not just linguistic competence but cultural immersion. We ask whether LLMs can learn this link: does fine-tuning on cultural data improve figurative language understanding, and vice versa? We conduct a systematic study across four models (ALLaM-7B, Fanar-1-9B, Qwen3-8B, Llama-3.1-8B) and six Arabic datasets spanning cultural commonsense, proverbs, and poetry across diverse dialects and regions. Fine-tuning on poetry improves idiom comprehension (+2.33%, p<0.05), a gain our ArabicMMLU control does not reproduce, indicating that it stems from figurative content rather than Arabic language adaptation and pointing to a sensitivity to non-literal meaning that transfers across figurative types. Cultural fine-tuning, by contrast, lowers proverb-interpretation accuracy in both Arabic-centric models. Transfer between the two domains is otherwise indistinguishable from noise, with Arabic models frequently regressing after fine-tuning, suggesting prior saturation of relevant knowledge, while multilingual models show greater adaptation headroom. Error analysis further reveals that fine-tuning reinforces experiential cultural knowledge while destabilizing historically grounded factual knowledge. Our findings suggest that the relationship between culture and figurative language, though conceptually natural, is not straightforwardly captured through fine-tuning alone.

Problem

• figurative language
• cultural data
• fine-tuning
• cross-domain transfer
• Arabic datasets

Innovation

• figurative language understanding
• cultural data fine-tuning
• cross-domain transfer
• Arabic models
• non-literal meaning